We introduce Noise2Music, where a series of diffusion models is trained ...
We present SingSong, a system that generates instrumental music to accom...
We introduce MusicLM, a model generating high-fidelity music from text
d...
AI tools increasingly shape how we discover, make and experience music. ...
Data is the lifeblood of modern machine learning systems, including for ...
An ideal music synthesizer should be both interactive and expressive,
ge...
We propose a new method for training a supervised source separation syst...
What audio embedding approach generalizes best to a wide range of downst...
Real-world data is high-dimensional: a book, image, or musical performan...
Musical expression requires control of both what notes are played, and h...
There is an increasing interest from ML and HCI communities in empowerin...
Automatic Music Transcription (AMT), inferring musical notes from raw au...
Automatic Music Transcription has seen significant progress in recent ye...
Score-based generative models and diffusion probabilistic models have be...
Semantically meaningful information content in perceptual signals is usu...
Classifier metrics, such as accuracy and F-measure score, often serve as...
Most generative models of audio directly generate samples in one of two
...
We consider the problem of learning high-level controls over the global
...
We explore models for translating abstract musical ideas (scores, rhythm...
Efficient audio synthesis is an inherently difficult machine learning ta...
End-to-end optimization has achieved state-of-the-art performance on man...
Generating musical audio directly with neural networks is notoriously
di...
Discovering and exploring the underlying structure of multi-instrumental...
The Variational Autoencoder (VAE) has proven to be an effective model fo...
In the quest towards general artificial intelligence (AI), researchers h...
Deep generative neural networks have proven effective at both conditiona...
We consider the problem of transcribing polyphonic piano music with an
e...
Generative models in vision have seen rapid progress due to algorithmic
...
We show that an end-to-end deep learning approach can be used to recogni...